System and method for detecting unwanted content

摘要

A system and method for detecting unwanted electronic content, such as spam. As a user operates an application to send messages, several metrics are tracked to allow the system to analyze her activity. Illustrative metrics may include, but are not limited to, block count (e.g., how many other users have blocked her), block rate (e.g., the rate at which other users block her), peer symmetry (e.g., percentage of her messages that are to other users that have her in their address book), message uniqueness (e.g., how unique her messages are from each other), peer uniqueness (e.g., how unique the addressees of her messages are), and message rate (e.g., the rate at which she sends messages). Periodically, metrics may be compared to corresponding thresholds. Depending on whether a threshold is crossed, and which threshold is crossed, she may be banned from using the application or placed on a watch list.

主权项

1. A method comprising:
receiving, at a server from a first user, an electronic message having one or more addressees; comparing a representation of the electronic message to representations of one or more electronic messages previously sent by the first user during a predetermined time period; if the electronic message was previously sent by the first user during the predetermined time period, incrementing a message count associated with the electronic message; if the electronic message was not previously sent by the first user during the predetermined time period, storing the representation of the electronic message; updating a message uniqueness metric in a manner depending on whether the electronic message had been sent previously during the predetermined time period; wherein the message uniqueness metric reflects a percentage of electronic messages sent by the first user during the predetermined time period that were unique; comparing the updated message uniqueness metric to a threshold message uniqueness value indicative of distribution of unwanted content; determining, based on the comparing of the updated message uniqueness metric, whether the electronic message contains unwanted content; delivering the electronic message if the updated message uniqueness metric indicates that the electronic message does not contain unwanted content; and refraining from delivering the electronic message if the updated message uniqueness metric indicates that the electronic message contains unwanted content.